Matching pursuit (MP), particularly using the Gammatones dic- tionary, has become a popular tool in sparse representations of speech/audio signals. The classical MP algorithm does not however take into account psychoacoustical aspects of the audi- tory system. Recently two algorithms, called PAMP and PMP have been introduced in order to select only perceptually rele- vant atoms during MP decomposition. In this paper we compare this two algorithms on few speech sentences. The results sug- gest that PMP, which also has the strong advantage of including an implicit stop criterion, always outperforms PAMP as well as classical MP. We then raise the question of whether the Gam- matones dictionary is the best choice when using PMP. We thus compare it to the popular Gabor and damped-Sinusoids dictio- naries. The results suggest that Gammatones always outperform damped-Sinusoids, and that Gabor yield better reconstruction quality but with higher atoms rate.